Active sequential learning with tactile feedback

Sethu Vijayakumar, Hannes Saal, Jo-Anne Ting

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We consider the problem of tactile discrimination, with the goal of estimating an underlying state parameter in a sequential setting. If the data is continuous and high- dimensional, collecting enough representative data samples becomes difficult. We present a framework that uses active learning to help with the sequential gathering of data samples, using information-theoretic criteria to find optimal actions at each time step. We consider two approaches to recursively update the state parameter belief: an analytical Gaussian approximation and a Monte Carlo sampling method. We show how both active frameworks improve convergence, demonstrating results on a real robotic hand-arm system that estimates the viscosity of liquids from tactile feedback data.
Original languageEnglish
Title of host publicationProc. 13th Int. Conf. on Artificial Intelligence and Statistics (AISTATS 2010), JMLR: W&CP 9:677-684, Chia Laguna, Sardinia, Italy (2010).
Number of pages8
Publication statusPublished - 2010


  • Informatics
  • Computer Science


Dive into the research topics of 'Active sequential learning with tactile feedback'. Together they form a unique fingerprint.

Cite this